Qwen3.8 Next
on AMD RX 7900 XTX · Strata
Use cases
coding
Summary
User reports Qwen3.8 Next at 45-50 t/s on an RX 7900 XTX with slow DDR4 system memory, using Strata with IQ3_XXS weights just under 80GB.
Setup is Strata with IQ3_XXS weights, MTP speculation enabled, and CPU offload to system RAM. Llama.cpp with tuning maxed out around 22.5 t/s on the same rig.
User notes similar results for 12GB and 16GB cards, faster numbers for DDR5 owners, and recommends against the Q2 weights.